A Single-Center Retrospective Analysis of Artificial Intelligence-Based Emotion Recognition Systems for Attention-Regulation Training in Children with Attention-Deficit/Hyperactivity Disorder
Introduction: Children with attention-deficit/hyperactivity disorder (ADHD) often experience attention instability and emotion dysregulation. Existing interventions typically lack real-time responsiveness and ecological validity. This study retrospectively examined historical training records from an AI-assisted closed-loop system integrating emotion recognition and behavioral feedback for attention regulation in children with ADHD. Methods: This single-center retrospective analysis included historical training records from 60 children with ADHD who had completed either AI-assisted attention training or conventional attention training between 2021 and 2024. The AI-assisted training-record group comprised children whose archived records included 12 sessions of integrated cognitive training involving Go/No-Go, CPT, and Flanker tasks with real-time AI-generated feedback based on task performance and facial-emotion monitoring. The conventional training-record group completed the same attention tasks without AI-based feedback. Assessments included task performance, Conners Continuous Performance Test, 3rd Edition (CPT-3), teacher ratings, and emotion metrics, analyzed using linear mixed-effects models, linear growth modeling, and structural equation modeling (SEM). Results: Compared with conventional training records, AI-assisted training records showed greater pre-post changes in reaction time (RT), RT variability, and task accuracy, together with fewer commission errors in CPT-3. Post-feedback behavioral recovery was observed in 78.3% of feedback events. Teacher ratings showed consistent pre-post improvements across attention maintenance, emotional regulation, and task execution. Negative emotion labels decreased from 42.3% to 24.6% (p = 0.003). SEM supported an associative pathway linking emotion recognition frequency, feedback frequency, and RT reduction (95% CI: 0.15-0.38). Conclusions: The retrospective findings suggest that AI-assisted closed-loop training records were associated with favorable changes in attention and emotional-state indicators in children with ADHD. These exploratory results support further prospective, externally validated studies before broader clinical or educational implementation.
Authors
- Chenggang Chen
- BinRong Chen
- Chunbao Zhi
- Lili Zhu
- Tingting Wang
Publication Details
- Journal
- Neuropsychobiology
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1159/nps/adyag004
- Primary Topic
- Attention Deficit Hyperactivity Disorder
- Type
- article
- Field-Weighted Citation Impact
- 0.00